Toggle light / dark theme

Synthesis AI, a startup that specializes in synthetic data technologies, announced that they have developed a new technology for digital human creation, which enables one to create highly realistic 3D digital humans from text prompts using generative AI and VFX pipelines.

The technology showcased by Synthesis AI allows users to input specific text descriptions such as age, gender, ethnicity, hairstyle, and clothing to generate a 3D model that matches the specifications. Users can also edit the 3D model by changing text prompts or using sliders to adjust features like facial expressions and lighting.

The earliest artificial neural network, the Perceptron, was introduced approximately 65 years ago and consisted of just one layer. However, to address solutions for more complex classification tasks, more advanced neural network architectures consisting of numerous feedforward (consecutive) layers were later introduced. This is the essential component of the current implementation of deep learning algorithms. It improves the performance of analytical and physical tasks without human intervention, and lies behind everyday automation products such as the emerging technologies for self-driving cars and autonomous chat bots.

The key question driving new research published today in Scientific Reports is whether efficient learning of non-trivial classification tasks can be achieved using brain-inspired shallow feedforward networks, while potentially requiring less .

“A positive answer questions the need for deep learning architectures, and might direct the development of unique hardware for the efficient and fast implementation of shallow learning,” said Prof. Ido Kanter, of Bar-Ilan’s Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center, who led the research. “Additionally, it would demonstrate how brain-inspired shallow learning has advanced computational capability with reduced complexity and energy consumption.”

While the scientific debate about the origin of water on our planet remains open, the truth is that relative to its size, Earth is more like a desert compared to other celestial bodies in our cosmic neighbourhood. Estimates vary, but there could be as much as 50 times more liquid water in the solar system than is found on Earth—an astonishing revelation that would have sounded absurd just a few decades ago. And scientists are eager to send spacecraft to this extraterrestrial water in the hope of discovering conditions suitable for life.

Apart from Earth, the inner solar system—containing the four planets closest to the Sun—is largely devoid of liquid water. On Mercury and Venus liquid water simply boils away, while on Mars any liquid water would quickly freeze or evaporate due to the low atmospheric pressure and temperature. Although there is some intriguing evidence that liquid water may exist beneath the Martian southern polar ice cap, the amounts would be very small compared to those found on Earth.

Paradoxically, to find to find an unexpected abundance of liquid water, we must venture into the frigid depths of the outer solar system, far from the warmth of the Sun. There, deep beneath the frozen surfaces of moons orbiting the gas giants Jupiter, Saturn, Uranus and Neptune, scientists have found strong evidence of vast oceans. But how can water remain liquid in such an extremely cold environment, where the Sun is only a faint glow in the sky and the warmest surface temperatures are always well below zero?